高级检索

    李绍军, 张小广. 基于Alopex的进化优化算法[J]. 华东理工大学学报(自然科学版), 2009, (2): 261-264.
    引用本文: 李绍军, 张小广. 基于Alopex的进化优化算法[J]. 华东理工大学学报(自然科学版), 2009, (2): 261-264.
    A New Evolutionary Optimization Algorithms Based on Alopex[J]. Journal of East China University of Science and Technology, 2009, (2): 261-264.
    Citation: A New Evolutionary Optimization Algorithms Based on Alopex[J]. Journal of East China University of Science and Technology, 2009, (2): 261-264.

    基于Alopex的进化优化算法

    A New Evolutionary Optimization Algorithms Based on Alopex

    • 摘要: 提出了一种基于Alopex的进化优化算法。该算法在进化过程中从种群中随机选择2个个体,通过计算2个个体和目标函数值的变化情况,确定算法进一步搜索方向的概率,逐步迭代最终收敛到全局最优。该算法具备基本进化算法的特点,同时具备Alopex算法的优点,即在一定程度上具有梯度下降法和模拟退火算法的优点。对典型函数的测试表明:新算法的全局搜索能力有了显著提高,特别是对多峰函数能够有效地避免早熟收敛问题。

       

      Abstract: A new evolutionary algorithm is proposed based on Alopex. By randomly selecting two individuals and computing the probability of searching direction, the proposed algorithm can converge to the globally optimal value. This algorithm has not only the basic characteristic of evolutionary algorithms, but also the advantage of gradient methods and simulation anneal algorithm to some extend. The experiment results show that the proposed algorithm is superior to standard evolutionary algorithms, especially for multiapices function.

       

    /

    返回文章
    返回